ConceptualAI ConceptualAI
Open Builder

Atelier

A visual booking marketplace: photo listings, schedules that can’t double-book, and a natural-language booking assistant.

Atelier screenshot
Open the live app ↗

What was asked for

This is the specification the app was generated from — one prompt, published in full and unedited, rather than a summary of it.

Build a visual marketplace for booking creative classes and studio sessions (for example pottery, photography, music, or cooking classes).

Users register with email and password, log in, and create a profile with a display name, a short bio, and an avatar image they can upload. Any user can act as a host or a guest.

Hosts create listings. A listing has a title, a description, a category, a location, a price, and one or more photos the host uploads. For each listing, the host publishes available time slots that guests can book.

Guests browse a visual grid of listings with their photos and can filter by category. Opening a listing shows its photos, details, available time slots, and reviews. A guest books an available time slot; the system must prevent two guests from booking the same slot. There is also a natural-language booking assistant: a guest can type a request like "find me a pottery class next Saturday morning" and the assistant finds matching listings and available slots and books one for them.

When a booking is made, a private message thread between the guest and the host is started for that booking, and that is where they arrange payment and any session specifics — the app itself does not process payments; the listing's price is what the host communicates and collects directly. After a session, a guest can leave a star rating and a written review on the listing. Users get a notification when they receive a new booking or a new message.

A host can delete one of their listings. When a listing is deleted, all of its time slots, bookings, reviews, and message threads connected to it are removed as well, leaving no orphaned data.

What got built

  • AI booking assistant
  • Scheduling & reservations
  • Messaging
  • Reviews
  • Media

Things you can actually do in it

The app is live and public. Without taking our word for anything, you can:

  • Scroll the photo grid and filter by category
  • Type "find me a pottery class next Saturday morning" — the assistant finds and books a slot
  • Booking opens a private message thread with the host
  • Try to double-book a taken slot — the server refuses

The code

The repositories are public: a Deno backend carrying the generated test suite, the OpenAPI spec and a Dockerfile, and a React frontend built against that same spec. This is the export a build hands you — clone it and read it.

Every one of them has exactly one commit: "Initial export from ConceptualAI". Nothing has been hand-fixed after the fact, and you do not have to take our word for that — the commit history is public, and a second commit would be sitting right there if we had.

Atelier-backend Atelier-frontend

Why this one is here

It has a real backend

Authentication, persisted data, and the integrations above are running server-side against a real database — not mocked, and not a frontend pretending.

Its tests are in the repository

The concepts underneath — data, auth, the state everything else depends on — are accepted only once their generated tests pass against a real database. Those tests shipped with the code, so you can run them yourself.

It runs without us

No proprietary runtime and no SDK in between. Clone the backend and it runs anywhere a container runs.

You would own this one

An equivalent build hands you both repositories on any plan — Free included, once you have the three credits a minimum build costs. See pricing.

Build something like this

If this looks like the thing you are trying to build, describe yours in the builder. If it looks like less than what you need, our honest comparison covers when an app builder or a development shop is the better call.

All case studies · App builders vs dev shops · Pricing · Terms · admin@conceptual-ai.app